Research map / Graph learning / Graph self-supervised learning
Graph Meta Learning via Local Subgraphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use local subgraphs with G-Meta rather than the strongest listed baseline | G-Meta · ogbn-arxiv | multi-class accuracy: 0.392\std{0.015} -> 0.451\std{0.032} | Helped |
| Use G-Meta rather than the strongest listed baseline | G-Meta · Tissue-PPI | multi-class accuracy: 0.745\std{0.051} -> 0.768\std{0.029} | Helped |
| Use G-Meta rather than the strongest listed baseline | G-Meta · Fold-PPI | multi-class accuracy: 0.482\std{0.062} -> 0.561\std{0.059} | Helped |
| Use G-Meta rather than the strongest listed baseline | G-Meta · FirstMM-DB | multi-class accuracy: 0.779\std{0.020} -> 0.784\std{0.028} | No clear effect |
| Use G-Meta rather than the strongest listed baseline | G-Meta · Tree-of-Life | multi-class accuracy: 0.719\std{0.012} -> 0.722\std{0.032} | No clear effect |
| Add MAML optimization-based meta-learning (ablation) | G-Meta · ogbn-arxiv | multi-class accuracy: 0.372\std{0.017} -> 0.451\std{0.032} | Helped |
| Add MAML optimization-based meta-learning (ablation) | G-Meta · Tissue-PPI | multi-class accuracy: 0.546\std{0.025} -> 0.768\std{0.029} | Helped |
| Add MAML optimization-based meta-learning (ablation) | G-Meta · Fold-PPI | multi-class accuracy: 0.382\std{0.031} -> 0.561\std{0.059} | Helped |
| Add MAML optimization-based meta-learning (ablation) | G-Meta · FirstMM-DB | multi-class accuracy: 0.779\std{0.020} -> 0.784\std{0.028} | No clear effect |
| Add MAML optimization-based meta-learning (ablation) | G-Meta · Tree-of-Life | multi-class accuracy: 0.697\std{0.010} -> 0.722\std{0.032} | Helped |
| Add prototypical loss (ablation) | G-Meta · ogbn-arxiv | multi-class accuracy: 0.389\std{0.021} -> 0.451\std{0.032} | Helped |
| Add prototypical loss (ablation) | G-Meta · Fold-PPI | multi-class accuracy: 0.482\std{0.062} -> 0.561\std{0.059} | Helped |
Closest papers by meaning
- When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract) (AAAI 2024 · similarity 0.89)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.87)
- Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024 · similarity 0.87)
- SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning (AAAI 2025 · similarity 0.87)
- Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees (ICML 2025 · similarity 0.86)
- Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.